activity
20242026
collaborators

24 papers

cs.LG2026

On the Safety of Graph Representation Learning

Xiaoguang Guo, Zehong Wang, Ziming Li +5

Graph representation learning (GRL) has evolved from topology-only graph embeddings to task-specific supervised GNNs, and more recently to reusable representations and graph founda…

cs.IR2026

What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context

Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang +2

What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that existing preference-alignment approache…

cs.CL2026

Semantic Refinement with LLMs for Graph Representations

Safal Thapaliya, Zehong Wang, Jiazheng Li +3

Graph-structured data exhibit substantial heterogeneity in where their predictive signals originate: in some domains, node-level semantics dominate, while in others, structural pat…

cs.LG2026

Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance

Jiachi Zhao, Zehong Wang, Yamei Liao +2

Graph generation is a fundamental problem in graph learning with broad applications across Web-scale systems, knowledge graphs, and scientific domains such as drug and material dis…

cs.CL2026

GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health

Jiatan Huang, Zheyuan Zhang, Tianyi Ma +4

Nutritional interventions are important for managing chronic health conditions, but current computational methods provide limited support for personalized dietary guidance. We iden…

cs.DL2026

LongDA: Benchmarking LLM Agents for Long-Document Data Analysis

Yiyang Li, Zheyuan Zhang, Tianyi Ma +4

We introduce LongDA, a data analysis benchmark for evaluating LLM-based agents under documentation-intensive analytical workflows. In contrast to existing benchmarks that assume we…